Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    attribute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hazards
    -0.07
     Accessories
    -0.07
    LEASE
    -0.06
     reefs
    -0.06
    altern
    -0.06
    icers
    -0.06
    	stat
    -0.06
    	This
    -0.06
    .High
    -0.06
    Names
    -0.06
    POSITIVE LOGITS
     дру
    0.07
     lethal
    0.07
     нему
    0.07
    νει
    0.07
    _probs
    0.07
     enfermed
    0.06
     -↵↵
    0.06
    نسية
    0.06
     lighten
    0.06
    岛
    0.06
    Act Density 0.000%

    No Known Activations